The H2020 MeMAD project ambitions to develop a set of technologies that will describe comprehensively videos, ranging from visual objects, people and motions that can be seen, to music, sounds and speech that can be hear and background knowledge and common sense that enable to understand the stories being told in those videos.
In this interview, Prof. Benoit Huet from EURECOM is giving hints on how recent developments in AI enable to tackle those objectives but also the outstanding scientific challenges that we are facing. Read the whole article here (in French only).